Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 109 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.2714. Min Act: -0.1700
Data Index: 329702 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.2243. Min Act: -0.1700
Data Index: 4385984 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.2086. Min Act: -0.1700
Data Index: 268639 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.1771. Min Act: -0.1700
Data Index: 7767337 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.1929. Min Act: -0.1700
Data Index: 8386485 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.1614. Min Act: -0.1700
Data Index: 4237466 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.1299. Min Act: -0.1700
Data Index: 1657683 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.1299. Min Act: -0.1700
Data Index: 5304771 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.1457. Min Act: -0.1700
Data Index: 4318528 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.1457. Min Act: -0.1700
Data Index: 8563793 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.1299. Min Act: -0.1700
Data Index: 2362348 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.1299. Min Act: -0.1700
Data Index: 3819904 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.1142. Min Act: -0.1700
Data Index: 8432303 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.1299. Min Act: -0.1700
Data Index: 7159788 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.0984. Min Act: -0.1700
Data Index: 1809721 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.1142. Min Act: -0.1700
Data Index: 5742953 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.0984. Min Act: -0.1700
Data Index: 7299260 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.0984. Min Act: -0.1700
Data Index: 898563 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.1142. Min Act: -0.1700
Data Index: 172967 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2714. Min Range: -3.2714
Max Act: 3.0984. Min Act: -0.1700
Data Index: 417875 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19